Suno Speech beta generates spoken audio and original music from text

Suno is widening its audio tools beyond songs. The company has started a beta for Speech, a model that takes text and turns it into spoken audio with original background music, all in one track.

The pitch is simple: type in an idea, a poem, or something you’ve written, then tell Suno what kind of voice and musical style you want. The result sits somewhere between narration and a fully scored piece, which is exactly why the company keeps describing it as a new kind of creative outlet rather than just another voice feature.

That framing fits the examples Suno says it found while building it. Friends’ text messages became overblown dramatic readings. Ordinary voice notes got absurdly grand scores. The team also used it for meditations, poems, pep talks, and bedtime stories for kids. Those aren’t polished demo cases. They’re the sort of things people already make in Suno for birthdays, weddings, inside jokes, faith, worship, and family moments.

Suno says it tested Speech with a small group of users over the past month before opening the beta to everyone. And the company is not pretending it’s finished. It warns that British accents may drift to Australia and back, and that dramatic pauses may get a little too dramatic. In other words, this is very much a beta.

Still, the move says a lot about where Suno wants to go. Music remains the center of the company’s work, but Speech pushes the product toward a broader idea of “creative entertainment,” where text can become something spoken, scored, and personal without much friction at all.